这不是重复项 它不同于OpenCL Vector add program。
我的代码输出一堆零,无法理解为什么会发生。
pool.py
我的内核函数是vectorCLKernel.cl
#include <stdio.h>
#include <CL/cl.h>
#include<stdlib.h>
//Max source size of the kernel string
#define MAX_SOURCE_SIZE (0x100000)
int main(void)
{
// Create the two input vectors
int i;
int LIST_SIZE;
printf("Enter how many elements:");
scanf("%d",&LIST_SIZE);
int *A = (int*) malloc (sizeof (int) * LIST_SIZE);
//Initialize the input vectors
for(i = 0; i < LIST_SIZE; i++)
{
A[i] = i; //if LIST_SIZE is very large
}
int *B = (int*)malloc(sizeof(int)*LIST_SIZE);
//Initialize the input vectors
for(i = 0; i < LIST_SIZE; i++)
{
B[i] = i+10;
}
int *C = (int*)malloc(sizeof(int)*LIST_SIZE);
// Load the kernel source code into the array source_str
FILE *fp;
char *source_str;
size_t source_size;
fp = fopen("vectorCLKernel.cl", "r");
if (!fp)
{
fprintf(stderr, "Failed to load kernel.\n");
getchar();
exit(1);
}
source_str = (char*)malloc(MAX_SOURCE_SIZE);
source_size = fread( source_str, 1, MAX_SOURCE_SIZE, fp);
fclose( fp );
// Get platform and device information
cl_platform_id platform_id = NULL;
cl_device_id device_id = NULL;
cl_uint ret_num_devices;
cl_uint ret_num_platforms;
cl_int ret = clGetPlatformIDs(1, &platform_id, &ret_num_platforms);
ret = clGetDeviceIDs( platform_id, CL_DEVICE_TYPE_GPU, 1,&device_id,&ret_num_devices);
// Create an OpenCL context
cl_context context = clCreateContext( NULL, 1, &device_id, NULL, NULL,&ret);
// Create a command queue
cl_command_queue command_queue = clCreateCommandQueue(context,device_id,NULL, &ret);
// Create memory buffers on the device for each vector A, B and C
cl_mem a_mem_obj = clCreateBuffer(context,CL_MEM_READ_ONLY,LIST_SIZE * sizeof(int), A, &ret);
cl_mem b_mem_obj = clCreateBuffer(context,CL_MEM_READ_ONLY,LIST_SIZE * sizeof(int), B, &ret);
cl_mem c_mem_obj = clCreateBuffer(context,CL_MEM_READ_WRITE,LIST_SIZE * sizeof(int), C, &ret);
// Copy the lists A and B to their respective memory buffers
ret = clEnqueueWriteBuffer(command_queue, a_mem_obj, CL_TRUE,0,LIST_SIZE * sizeof(int), A, 0, NULL, NULL);
ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE,0,LIST_SIZE * sizeof(int), B, 0, NULL, NULL);
// Create a program from the kernel source
printf("%s\n",source_str);
printf("%d\n",source_size);
cl_program program = clCreateProgramWithSource(context, 1, (const
char**)&source_str, (const size_t *)&source_size, &ret);
ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
// Create the OpenCL kernel object
cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
// Set the arguments of the kernel
ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&a_mem_obj);
ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&b_mem_obj);
ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *)&c_mem_obj);
// Execute the OpenCL kernel on the array
size_t global_item_size = LIST_SIZE;
size_t local_item_size = 1;
//Execute the kernel on the device
cl_event event;
ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,
&global_item_size, &local_item_size, 0, NULL, NULL);
ret = clFinish(command_queue);
// Read the memory buffer C on the device to the local variable C
ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0,LIST_SIZE
* sizeof(int), C, 0, NULL, NULL);
// Display the result to the screen
for(i = 0; i < LIST_SIZE; i++)
printf("%d + %d = %d\n", A[i], B[i], C[i]);
// Clean up
ret = clFlush(command_queue);
ret = clReleaseKernel(kernel);
ret = clReleaseProgram(program);
ret = clReleaseMemObject(a_mem_obj);
ret = clReleaseMemObject(b_mem_obj);
ret = clReleaseMemObject(c_mem_obj);
ret = clReleaseCommandQueue(command_queue);
ret = clReleaseContext(context);
free(A);
free(B);
free(C);
getchar();
return 0;
}
我已经正确编译了代码,但是不明白为什么我的输出为零
0 + 10 = 0
1 + 11 = 0
2 + 12 = 0
3 + 13 = 0
4 + 14 = 0
答案 0 :(得分:1)
首先,我建议您养成创建和使用一些C宏来检查每个OpenCL API调用中的错误的习惯。它将使您的生活更加轻松。
2,问题是您对clCreateBuffer的调用无效(全部三个)。注意:
clCreateBuffer(context,CL_MEM_READ_ONLY,LIST_SIZE * sizeof(int), A, &ret);
您要提供host_ptr参数。 clCreateBuffer的文档说:
CL_INVALID_HOST_PTR (如果host_ptr为NULL且在标志中设置了CL_MEM_USE_HOST_PTR或CL_MEM_COPY_HOST_PTR),或者如果host_ptr不为NULL但未设置CL_MEM_COPY_HOST_PTR或CL_MEM_USE_HOST_P> 。
...只是在其中放置NULL而不是A / B / C。